© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51272
    Prev
    Next
    INDEX
    Explanations

    code comments and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çª
    -0.07
    omm
    -0.07
    \/
    -0.07
    çĽĸ
    -0.07
    Ŀ¼
    -0.06
    ruz
    -0.06
     sorte
    -0.06
    atici
    -0.06
    èĪ
    -0.06
    men
    -0.06
    POSITIVE LOGITS
    åĬŁåIJį
    0.07
    ×ŀ×ķש
    0.07
    çİ°åľ¨çľĭæĿ¥
    0.07
    è²Ķ
    0.07
    èĩªå·±çļĦ缮æłĩ
    0.07
    wer
    0.07
    oins
    0.07
    ç¯ĩä¸ī
    0.07
    åĨįæİ¥
    0.07
    ingan
    0.07
    Activations Density 0.016%

    No Known Activations